Journal of Functional Morphology and Kinesiology

Background: Artificial intelligence (AI) is increasingly applied to physiological prediction, physical activity monitoring, and personalized exercise prescription. However, evidence regarding its practical effectiveness remains heterogeneous. This systematic review examined applications of AI, machine learning (ML), and deep learning (DL) in exercise-related prediction, monitoring, and personalization among adults. Methods: Following PRISMA 2020 guidelines, PubMed and Scopus were searched for studies published between 2015 and 2025, with Google Scholar used as a supplementary source. Eligibility followed PICO: adults aged 18 years or older (P); AI, ML, or DL applications for exercise prediction, monitoring, or personalization (I); conventional or non-personalized approaches, where applicable (C); and predictive accuracy and physiological, functional, or behavioral exercise outcomes (O). Findings were synthesized descriptively. Results: Ten studies were included: four examined physiological or energy-expenditure prediction, two investigated activity-related behavioral outcomes, two evaluated training-response classification or recommendation generation, and two assessed AI-personalized exercise interventions. Predictive models demonstrated promising performance in specific applications, although validation procedures and populations varied substantially. The intervention studies reported greater perceived exercise intensity and satisfaction in one trial and improvements in selected measures of balance, flexibility, and strength in another. Conclusions: AI-based approaches show potential for supporting exercise assessment, monitoring, and individualized decision-making. However, evidence regarding their superiority over conventional exercise prescription remains limited by the small number of intervention studies, methodological heterogeneity, and insufficient external validation. Further well-designed, long-term intervention studies are needed to establish their comparative effectiveness and practical benefits.

Background and Objectives: Non-specific low back pain (LBP) is multifactorial. Fascia of the thoracolumbar and lumbogluteal system showing stacking fascia—a layered, hyperechoic ultrasound appearance—may be an under-recognized peripheral source; routine imaging assesses the disc, vertebra, and nerve root but not these tissues. The objective is to describe a multi-point ultrasound-guided fascia hydrorelease (US-FHR) protocol, based on our clinical experience, for LBP in which involvement of the fascia is suspected from the history, the physical findings, and stacking fascia on ultrasound, after excluding red flags and clear radiculopathy. Methods: Narrative synthesis of targeted literature searches and our clinical experience; no formal consensus process or new prospective dataset. Results: Fourteen release points are described with rationale, technique, safety notes, and an ultrasound still. Conclusions: The diagnostic steps and their correspondences with the release points are based largely on our clinical experience and have not been validated. US-FHR is proposed not as a stand-alone treatment but as one element of multimodal care, in which the period of pain relief is used to resume active exercise. It is offered as the basis for prospective validation studies, distinct from the single-site thoracolumbar fascia (TLF) pilot NCT06818175.

Background: Soccer demands repeated high-intensity, powerful actions, which increase the risk of lower-limb injuries as fatigue accumulates in the working muscles. The hamstrings-to-quadriceps (H:Q) ratio is widely used to assess knee strength balance. Several studies have reported that fatigue can significantly decrease the H:Q ratio. Therefore, the objective of the present systematic review was to analyze the effect of simulated soccer-induced fatigue on the conventional and functional isokinetic H:Q ratios in soccer players. Methods: Eligibility required injury-free soccer players aged ≥ 18 years, 45- or 90-min running-based simulated soccer protocols, and pre-post H:Q data; injured samples and reports lacking relevant outcomes were excluded. MEDLINE (via PubMed), Web of Science, and SPORTDiscus were searched from inception to 6 April 2026. The following keywords were used: “soccer,” “muscle fatigue,” “hamstrings,” “H:Q ratio,” “isokinetic strength.” Quality was assessed using the 12-item National Heart, Lung, and Blood Institute tool for uncontrolled before–after studies. Findings were synthesized narratively. Results: Ten studies (155 participants) met the inclusion criteria, all assessing the H:Q ratio before and after a simulated soccer protocol. Most studies reported a significant decrease in the functional ratio of the dominant leg after different simulated soccer protocols. Conclusions: Simulated soccer-induced fatigue can reduce the H:Q ratios, but these changes reflect altered knee strength balance rather than direct evidence of increased injury risk. Future studies should use more advanced, field-simulated soccer protocols or real competitions to evaluate the H:Q ratio and whether its changes are associated with injury risk and develop rehabilitation strategies focused on delaying fatigue.